Computer Science – Computation and Language
Scientific paper
1994-11-05
Computer Science
Computation and Language
12 pages, Latex Postscript, compressed, uuencoded, will be presented in TWLT-8
Scientific paper
A new tightly coupled speech and natural language integration model is presented for a TDNN-based large vocabulary continuous speech recognition system. Unlike the popular n-best techniques developed for integrating mainly HMM-based speech and natural language systems in word level, which is obviously inadequate for the morphologically complex agglutinative languages, our model constructs a spoken language system based on the phoneme-level integration. The TDNN-CYK spoken language architecture is designed and implemented using the TDNN-based diphone recognition module integrated with the table-driven phonological/morphological co-analysis. Our integration model provides a seamless integration of speech and natural language for connectionist speech recognition systems especially for morphologically complex languages such as Korean. Our experiment results show that the speaker-dependent continuous Eojeol (word) recognition can be integrated with the morphological analysis with over 80\% morphological analysis success rate directly from the speech input for the middle-level vocabularies.
No associations
LandOfFree
Phoneme-level speech and natural language intergration for agglutinative languages does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Phoneme-level speech and natural language intergration for agglutinative languages, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Phoneme-level speech and natural language intergration for agglutinative languages will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-625256